Bio Atac Seq Deep Learning Atac

Version Compatibility

Reference examples tested with: chrombpnet 0.1.7+, bpnet-lite 0.6+ (DOI 10.5281/zenodo.7011327), scBasset 0.1.0+ (basenji2 fork), tangermeme 0.1+, tfmodisco-lite 2.2+, DeepLIFT 0.6+, captum 0.7+, tensorflow 2.13+, pytorch 2.1+, kipoi 0.8+.

Verify before use:

• Python: pip show then help(module.function) to check signatures
• CLI: --version then --help to confirm flags

If code throws unexpected errors, introspect the installed package and adapt rather than retrying. Deep-learning tooling evolves rapidly; method papers post 2023 may have superseded reference implementations.

Sequence-Based Deep Learning for ATAC-seq

"Score the effect of a GWAS SNP on chromatin accessibility" -> Train (or use pre-trained) sequence-to-accessibility CNNs that take 1-5 kb DNA windows and predict per-base Tn5 cleavage profiles. Outputs include: bias-corrected accessibility, single-base mutation effect predictions, and DeepLIFT contribution scores convertible to motifs via TF-MoDISco.

• CLI: chrombpnet pipeline --bigwig signal.bw --bigwig-bias bias.bw ...
• Python: bpnet-lite for custom architectures; tangermeme for fast scoring
• Python (single-cell): scBasset for per-cell sequence-based predictions
• Python (long-context): EnFormer pre-trained models via Kipoi

Sequence models are NOT a replacement for MACS+TOBIAS at every step. They excel at three specific tasks where classical pipelines struggle: (1) Tn5 bias correction in low-complexity sequence contexts, (2) variant effect prediction in non-genic regions, (3) cell-type-specific motif discovery beyond what JASPAR provides.

Algorithmic Taxonomy

| Tool | Architecture | Training | Output | Strength | Fails when | |------|-------------|----------|--------|----------|------------| | chromBPNet (Pampari 2025 Nat Genet) | Two-track CNN: bias model + accessibility model; bias trained on naked-DNA control or k-mer baseline, accessibility trained on chromatin signal | Per-cell-type, paired bias track | Bias-corrected per-base profile + total counts | Best-in-class bias correction; established in Kundaje lab pipelines | Requires GPU, ~24h training per cell type; needs >= 50M reads | | BPNet (Avsec 2021 Nat Genet 53:354) | Original counts + profile dual-head CNN | TF ChIP-seq or ATAC | Per-base profile prediction | Foundational; widely cited; bpnet-lite reimpl maintained | Less polished than chromBPNet for ATAC; bias correction needs separate model | | scBasset (Yuan & Kelley 2022) | Basenji2-derived CNN, per-cell projection layer | Single-cell ATAC | Per-cell sequence-derived peak score | First sequence model that predicts per-cell accessibility; outperforms chromVAR for cluster discrimination | Fixed architecture, hard to extend; benchmarks evolving | | EnFormer (Avsec 2021 Nat Methods 18:1196) | Long-context Transformer (196 kb input) | Reference epigenome (DNase + histones + CAGE) | Per-bin epigenome prediction | Best for distal regulation modeling; pre-trained available | Pre-trained models cell-line specific; finetuning on custom data is expensive | | Borzoi (Linder 2025 Nat Genet) | EnFormer extension trained on RNA + ATAC | Multi-tissue paired data | Sequence -> RNA + chromatin | Recent SOTA for variant effect on RNA via ATAC linkage | Newer; benchmarks still emerging | | DeepATAC / Basset (legacy) | Earlier CNN architectures | -- | Binary peak prediction | Historical context; cited in older literature | Superseded by chromBPNet + EnFormer; do not use for new work | | tangermeme | Inference-only fast wrapper | Use any saved model | Marginal scoring of variants | Speeds up variant effect prediction 100x; works with chromBPNet/BPNet outputs | Inference only; cannot train |

Methodology evolves; verify against current Kundaje lab pipelines (chrombpnet GitHub), Greenleaf lab (scBasset), and Avsec / Linder publications before locking pipelines.

When Deep Learning Helps vs When Classical Pipelines Suffice

| Task | Classical | Deep Learning | |------|-----------|---------------| | Peak calling | MACS3 / Genrich (sufficient) | chromBPNet (overkill unless variant downstream) | | Tn5 bias correction at TF motifs | TOBIAS ATACorrect (good) | chromBPNet (better at hard cases: low-complexity flanks, deep TF footprints) | | Differential accessibility | DiffBind / DESeq2 (sufficient) | -- (no clear DL advantage) | | GWAS variant effect prediction at causal SNPs | Limited (overlap heuristics) | chromBPNet / EnFormer (essential) | | Motif discovery from de novo data | MEME / HOMER (good) | chromBPNet + TF-MoDISco (better; finds composite + cooperative motifs) | | Per-cell TF activity | chromVAR (sufficient at the cluster level) | scBasset (better at fine-grained cell states) | | Cross-cell-type accessibility prediction | -- | EnFormer / Borzoi (only option) | | Predicting cell-type-specific enhancer activity from sequence | -- | chromBPNet / EnFormer (essential) |

For most standard ATAC analysis, classical pipelines remain primary. Deep learning enters when (a) variant interpretation is the goal, (b) cell-type prediction is needed beyond observed data, or (c) bias correction quality is paramount (low-input, FFPE, transcription factors with weak motifs).

Per-Tool Failure Modes

chromBPNet -- Bias model mismatch

Trigger: Training the bias model on a dataset different from the accessibility dataset (e.g. K562 bias model used on primary T cells).

Mechanism: chromBPNet's bias model captures sequence-specific Tn5 preference, which is mostly cell-type-invariant BUT contributions of chromatin context at cuts can vary. Cross-celltype bias models work but with degraded performance.

Symptom: Predicted footprints look correct at known TFs (CTCF) but fail on cell-type-specific regulators.

Fix: Train a per-cell-type bias model from naked-DNA control if available, OR use the chromBPNet authors' pre-trained k562 / GM12878 / HepG2 bias as a fallback (acknowledged degradation).

chromBPNet -- Insufficient training data

Trigger: Training on 1 typical for strong-effect SNPs in regulatory regions.

Reconciliation

| Pattern | Likely cause | Action | |---------|--------------|--------| | chromBPNet predicts strong effect; MACS does not call peak | Sequence model captures latent regulatory potential | Trust chromBPNet for variant effect; not for peak calling | | EnFormer prediction differs from chromBPNet at same locus | Different context windows (196 kb vs 1-2 kb); different cell types | Both can be correct at different scales; report both with their context size | | TF-MoDISco motifs differ from JASPAR | Different methodology (sequence-based vs ChIP-validated) | TF-MoDISco can find composites and cooperative; check JASPAR for confirmation | | chromBPNet bias correction differs from TOBIAS ATACorrect | Different bias models (CNN vs k-mer) | chromBPNet is more accurate but slower; TOBIAS still publishable for standard use |

Operational rule: For high-confidence variant prediction, agree across two approaches: chromBPNet + EnFormer (or Borzoi). Single-tool calls should be reported as exploratory. For motif discovery, validate TF-MoDISco hits against JASPAR/HOCOMOCO before publication.

GPU and Compute Considerations

| Task | Hardware | Wall time | |------|---------|-----------| | chromBPNet training (per cell type) | 1 A100 GPU, 80 GB RAM | ~24 h | | chromBPNet inference at 1M variants | 1 A100 | ~4 h | | EnFormer pre-trained inference | 1 V100+ | ~30 min for 100k variants | | Borzoi training | 1 A100, ~250 GB RAM | ~7 days | | scBasset training (10k cells) | 1 V100, 32 GB RAM | ~12 h | | TF-MoDISco on 1M peaks | CPU 32 cores | ~6 h |

For most labs without sustained GPU access: use pre-trained chromBPNet/EnFormer models for inference; only train custom models when the cell type is not in the public model zoo (encodeproject.org/atac-seq pre-trained chromBPNet).

Common Errors

| Error / symptom | Cause | Solution | |-----------------|-------|----------| | chromBPNet bias.h5 missing | Bias model training failed silently | Re-run chrombpnet bias pipeline with verbose; check input BAM size | | Out of memory during training | Default batch size too large for GPU | --batch-size 64 or smaller; reduce --num-filters | | Predicted profile is constant | Model collapsed (training too short) | Increase epochs; verify input peaks are non-empty | | TF-MoDISco produces too many small clusters | target_seqlet_fdr too loose | Tighten to 0.01; or increase flank_size | | EnFormer prediction has wrong shape | Pre-trained model expects 196 kb input | Pad input to exactly 196,608 bp | | Variant effect predictions cluster near zero | SNP outside model's effective window | Predict on window-centered sequences (variant at the center) | | chromBPNet model not converging | Peaks file contains chrM or blacklist | Pre-filter; chromBPNet does not auto-filter | | scBasset training crashes on Apple Silicon | TensorFlow Metal incompatible with operations | Use CPU mode or run on Linux GPU |

References

• Pampari A et al 2025 Nat Genet (chromBPNet; Tn5 bias correction with deep learning; consult current publication for exact volume/pages)
• Avsec Z et al 2021 Nat Genet 53:354-366 (BPNet; foundational sequence-to-profile)
• Avsec Z et al 2021 Nat Methods 18:1196-1203 (EnFormer; long-context Transformer)
• Linder J et al 2025 Nat Genet (Borzoi; multi-tissue sequence-to-RNA+chromatin; consult current publication for exact volume/pages)
• Yuan H & Kelley DR 2022 Nat Methods 19:1088 (scBasset)
• Shrikumar A et al 2017 ICML (DeepLIFT)
• Schreiber J et al 2024 (tangermeme; fast inference utilities)
• Shrikumar A et al 2018 bioRxiv (TF-MoDISco)
• Kelley DR 2020 Genome Res 30:1133 (Basenji2; precursor)

Related Skills

• atac-seq/atac-peak-calling - Classical peak calling input
• atac-seq/footprinting - Use chromBPNet bias correction as TOBIAS alternative
• atac-seq/motif-deviation - chromVAR vs scBasset for per-cell motif activity
• atac-seq/single-cell-atac - scBasset integration with sc workflow
• atac-seq/enhancer-gene-linking - Variant effect feeds enhancer scoring
• atac-seq/allele-specific-accessibility - DL-predicted variant effects vs observed allelic imbalance
• causal-genomics/fine-mapping - Downstream use of variant effect scores
• machine-learning/biomarker-discovery - General ML patterns
• gene-regulatory-networks/scenic-regulons - Combine motif discovery with TF networks

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: GPTomics
• Source: GPTomics/bioSkills
• License: MIT

Install and usage instructions live in the source repository linked above.